Skip to content

Feature Request: Add support for running against a local Ollama-hosted model #28

Description

@poiley

Add support for running a local model running on Ollama. The user should be able to specify the model ID by parameter like --model. We should assume the Ollama server runs on localhost:11434 but also allow the user to configure this by passing in the argument --server.

Error handling should be robust, logging should be clear but clean. This should support Windows, MacOS, and Linux.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Fields

No fields configured for Feature.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions